logoalt Hacker News

esafaktoday at 3:06 AM2 repliesview on HN

Alignment is the architectural solution. Make it so the model can't misbehave. Yet many people here deride it as tainting the model, claiming "Whose values is it aligned to?" Sandboxes are a last ditch layer. They fail, as we see.


Replies

startup_zombie_today at 4:11 AM

The “make it so the model can't misbehave” part is interesting. Maybe the goal isn't to make the model perfectly aligned, but to make misalignment have a very small blast radius. That feels like a more achievable engineering problem.

_vertigotoday at 3:50 AM

> Make it so the model can't misbehave.

How do you figure? I haven't met anyone who thinks that's possible. It seems clear to me that it is not possible.

show 1 reply